[Intel-gfx] [PATCH 07/12] drm/i915/guc: Improve the GuC documentation & comments about proxy submissions

[Oscar Mateo]

While at it, fix a typo (s/ring_lcra/ring_lrca) and improve the naming of one
firware interface field (s/ring_tail/submit_element_info, since it can contain
more than just the ring tail).

No change in functionality.

v2:
  - Remove reference to "unique user" of the GuC (Daniele)
  - Keep mention to renaming from "GuC context" to "client" (Daniele)

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo at intel.com>
---
 drivers/gpu/drm/i915/i915_guc_submission.c | 42 +++++++++++++++++++-----------
 drivers/gpu/drm/i915/intel_guc_fwif.h      |  4 +--
 drivers/gpu/drm/i915/intel_uc.h            |  6 +++--
 3 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index ff8235a1..855112d 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -30,16 +30,25 @@
 /**
  * DOC: GuC-based command submission
  *
- * i915_guc_client:
- * We use the term client to avoid confusion with contexts. A i915_guc_client is
- * equivalent to GuC object guc_context_desc. This context descriptor is
- * allocated from a pool of 1024 entries. Kernel driver will allocate doorbell
- * and workqueue for it. Also the process descriptor (guc_process_desc), which
- * is mapped to client space. So the client can write Work Item then ring the
- * doorbell.
+ * GuC client:
+ * A i915_guc_client refers to a submission path through GuC. Currently, there
+ * is only one of these (the execbuf_client) and this one is charged with all
+ * submissions to the GuC. This struct is the owner of a doorbell, a process
+ * descriptor and a workqueue (all of them inside a single gem object that
+ * contains all required pages for these elements).
  *
- * To simplify the implementation, we allocate one gem object that contains all
- * pages for doorbell, process descriptor and workqueue.
+ * GuC context descriptor:
+ * During initialization, the driver allocates a static pool of 1024 such
+ * descriptors, and shares them with the GuC.
+ * Currently, there exists a 1:1 mapping between a i915_guc_client and a
+ * guc_context_desc (via the client's context_index), so effectively only
+ * one guc_context_desc gets used. This context descriptor lets the GuC know
+ * about the doorbell, workqueue and process descriptor. Theoretically, it also
+ * lets the GuC know about our HW contexts (Context ID, etc...), but we actually
+ * employ a kind of submission where the GuC uses the LRCA sent via the work
+ * item instead (the single guc_context_desc associated to execbuf client
+ * contains information about the default kernel context only, but this is
+ * essentially unused). This is called a "proxy" submission.
  *
  * The Scratch registers:
  * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
@@ -308,10 +317,17 @@ static void guc_ctx_desc_init(struct intel_guc *guc,
 		if (!ce->state)
 			break;	/* XXX: continue? */
 
+		/*
+		 * XXX: When this is a GUC_CTX_DESC_ATTR_KERNEL client (proxy
+		 * submission or, in other words, not using a direct submission
+		 * model) the KMD's LRCA is not used for any work submission.
+		 * Instead, the GuC uses the LRCA of the user mode context (see
+		 * guc_wq_item_append below).
+		 */
 		lrc->context_desc = lower_32_bits(ce->lrc_desc);
 
 		/* The state page is after PPHWSP */
-		lrc->ring_lcra =
+		lrc->ring_lrca =
 			guc_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
 				(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
@@ -341,10 +357,6 @@ static void guc_ctx_desc_init(struct intel_guc *guc,
 	desc->wq_addr = gfx_addr + client->wq_offset;
 	desc->wq_size = client->wq_size;
 
-	/*
-	 * XXX: Take LRCs from an existing context if this is not an
-	 * IsKMDCreatedContext client
-	 */
 	desc->desc_private = (uintptr_t)client;
 }
 
@@ -468,7 +480,7 @@ static void guc_wq_item_append(struct i915_guc_client *client,
 	/* The GuC wants only the low-order word of the context descriptor */
 	wqi->context_desc = (u32)intel_lr_context_descriptor(rq->ctx, engine);
 
-	wqi->ring_tail = tail << WQ_RING_TAIL_SHIFT;
+	wqi->submit_element_info = tail << WQ_RING_TAIL_SHIFT;
 	wqi->fence_id = rq->global_seqno;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 3ae8cef..4edf40f 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -251,7 +251,7 @@ struct guc_doorbell_info {
 struct guc_wq_item {
 	u32 header;
 	u32 context_desc;
-	u32 ring_tail;
+	u32 submit_element_info;
 	u32 fence_id;
 } __packed;
 
@@ -278,7 +278,7 @@ struct guc_execlist_context {
 	u32 context_desc;
 	u32 context_id;
 	u32 ring_status;
-	u32 ring_lcra;
+	u32 ring_lrca;
 	u32 ring_begin;
 	u32 ring_end;
 	u32 ring_next_free_location;
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index 3ec54a1..65d0b59 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -34,7 +34,9 @@
 
 /*
  * This structure primarily describes the GEM object shared with the GuC.
- * The GEM object is held for the entire lifetime of our interaction with
+ * The specs sometimes refer to this object as a "GuC context", but we use
+ * the term "client" to avoid confusion with hardware contexts. This
+ * GEM object is held for the entire lifetime of our interaction with
  * the GuC, being allocated before the GuC is loaded with its firmware.
  * Because there's no way to update the address used by the GuC after
  * initialisation, the shared object must stay pinned into the GGTT as
@@ -44,7 +46,7 @@
  *
  * The single GEM object described here is actually made up of several
  * separate areas, as far as the GuC is concerned. The first page (kept
- * kmap'd) includes the "process decriptor" which holds sequence data for
+ * kmap'd) includes the "process descriptor" which holds sequence data for
  * the doorbell, and one cacheline which actually *is* the doorbell; a
  * write to this will "ring the doorbell" (i.e. send an interrupt to the
  * GuC). The subsequent  pages of the client object constitute the work
-- 
1.9.1